Search Results (2)

Navigating the complexity of petroleum futures markets—marked by extreme volatility, geopolitical uncertainty, and macroeconomic shocks—demands adaptive and risk-sensitive strategies. This paper explores an Adaptive Risk-sensitive Transformer-based Deep Reinforcement Learning (ART-DRL) framework to improve portfolio optimization in commodity futures trading. While deep reinforcement learning (DRL) has been applied in equities and forex, its use in commodities remains underexplored. We evaluate DRL models, including Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Deep Deterministic Policy Gradient (DDPG), integrating dynamic reward functions and asset-specific optimization. Empirical results show improvements in risk-adjusted performance, with an annualized return of 1.353, a Sharpe Ratio of 4.340, and a Sortino Ratio of 57.766. Although the return is below DQN (1.476), the proposed model achieves better stability and risk control. Notably, the models demonstrate resilience by learning from historical periods of extreme volatility, including the COVID-19 pandemic (2020–2021) and geopolitical shocks such as the Russia–Ukraine conflict (2022), despite testing commencing in January 2023. This research offers a practical, data-driven framework for risk-sensitive decision-making in commodities, showing how machine learning can support portfolio management under volatile market conditions. Full article

The research presented in this article is dedicated to analyzing the acceptability of traditional techniques of statistical management decision-making in conditions of stochastic chaos. A corresponding example would be asset management at electronic capital markets. This formulation of the problem is typical for a large number of applications in which the managed object interacts with an unstable immersion environment. In particular, this issue arises in problems of managing gas-dynamic and hydrodynamic turbulent flows. We highlight the features of observation series of the managed object’s state immersed in an unstable interaction environment. The fundamental difference between observation series of chaotic processes and probabilistic descriptions of traditional models is demonstrated. We also present an additive observation model with a chaotic system component and non-stationary noise which provides the most adequate characterization of the original observation series. Furthermore, we suggest a method for numerically analyzing the efficiency of conventional statistical solutions in the conditions of stochastic chaos. Based on numerical experiments, we establish that techniques of optimal statistical synthesis do not allow for making effective management decisions in the conditions of stochastic chaos. Finally, we propose several versions of compositional algorithms focused on the adaptation of statistical techniques to the non-deterministic conditions caused by the specifics of chaotic processes. Full article